© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9356
    Prev
    Next
    INDEX
    Explanations

    terms related to parental involvement and educational factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "parental", "bronchial," or "judicial"

    np_acts-logits-general · gemini-2.0-flash

    parental educational level, involvement, or acknowledgement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assoluto
    -0.60
     religieuses
    -0.60
     marito
    -0.59
     of
    -0.58
    役
    -0.57
     accepté
    -0.57
     prêtres
    -0.56
     dieux
    -0.55
     isolado
    -0.54
     réguli
    -0.54
    POSITIVE LOGITS
     '\\;'
    0.85
    ")));
    
    0.85
    ')";
    0.83
    }')
    0.82
    ']);
    
    0.82
    [])
    
    0.81
    []);
    0.81
    BibitemShut
    0.79
    '])
    
    0.78
    "]);
    
    0.77
    Activations Density 0.805%

    No Known Activations